Revisions V3 - Favicons and minor HTML updates

.gitignore

@@ -164,4 +164,5 @@ cython_debug/
 /src/__pycache__
 /utils/__pycache__
 /__pycache__
-/temp_models
+/temp_models
+/modules/__pycache__

README.md

@@ -4,53 +4,64 @@ emoji: 🌖
 colorFrom: yellow
 colorTo: purple
 sdk: gradio
+python_version: 3.10.13
 sdk_version: 5.16.0
 app_file: app.py
-pinned: true
-license: creativeml-openrail-m
-short_description: '[ 250+ Impressive LoRA For Flux ]'
+pinned: false
+short_description: Transform Your Images into Mesmerizing Hexagon Grids
+license: apache-2.0
+tags:
+- map maker
+- tabletop
+- hexagon
+- text-to-image
+- image-generation
+- flux
+- depth
+- 3d
+hf_oauth: true
+fullWidth: true
 thumbnail: >-
-  https://cdn-uploads.huggingface.co/production/uploads/6346595c9e5f0fe83fc60444/9dqqr3iMjoNdXWzDTV42-.png
+  https://cdn-uploads.huggingface.co/production/uploads/6346595c9e5f0fe83fc60444/s0fQvcoiSBlH36AXpVwPi.png
 ---
 
-# List of Flux Dev LoRA Repositories Used as of Now 
+# Hex Game Maker
+## Description
+Welcome to Hex Game Maker, the ultimate tool for transforming your images into mesmerizing hexagon grid masterpieces! Whether you're a tabletop game enthusiast, a digital artist, or just someone who loves unique patterns, Hex Game Maker has something for you.
 
-| No. | Repository Name | Link |
-| --- | --------------- | ---- |
-| 1   | Canopus-LoRA-Flux-FaceRealism | [Link](https://huggingface.co/prithivMLmods/Canopus-LoRA-Flux-FaceRealism) |
-| 2   | softserve_anime | [Link](https://huggingface.co/alvdansen/softserve_anime) |
-| 3   | Canopus-LoRA-Flux-Anime | [Link](https://huggingface.co/prithivMLmods/Canopus-LoRA-Flux-Anime) |
-| 4   | FLUX.1-dev-LoRA-One-Click-Creative-Template | [Link](https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-One-Click-Creative-Template) |
-| 5   | Canopus-LoRA-Flux-UltraRealism-2.0 | [Link](https://huggingface.co/prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0) |
-| 6   | Flux-Game-Assets-LoRA-v2 | [Link](https://huggingface.co/gokaygokay/Flux-Game-Assets-LoRA-v2) |
-| 7   | softpasty-flux-dev | [Link](https://huggingface.co/alvdansen/softpasty-flux-dev) |
-| 8   | FLUX.1-dev-LoRA-add-details | [Link](https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-add-details) |
-| 9   | frosting_lane_flux | [Link](https://huggingface.co/alvdansen/frosting_lane_flux) |
-| 10  | flux-ghibsky-illustration | [Link](https://huggingface.co/aleksa-codes/flux-ghibsky-illustration) |
-| 11  | FLUX.1-dev-LoRA-Dark-Fantasy | [Link](https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-Dark-Fantasy) |
-| 12  | Flux_1_Dev_LoRA_Paper-Cutout-Style | [Link](https://huggingface.co/Norod78/Flux_1_Dev_LoRA_Paper-Cutout-Style) |
-| 13  | mooniverse | [Link](https://huggingface.co/alvdansen/mooniverse) |
-| 14  | pola-photo-flux | [Link](https://huggingface.co/alvdansen/pola-photo-flux) |
-| 15  | flux-tarot-v1 | [Link](https://huggingface.co/multimodalart/flux-tarot-v1) |
-| 16  | Flux-Dev-Real-Anime-LoRA | [Link](https://huggingface.co/prithivMLmods/Flux-Dev-Real-Anime-LoRA) |
-| 17  | Flux_Sticker_Lora | [Link](https://huggingface.co/diabolic6045/Flux_Sticker_Lora) |
-| 18  | flux-RealismLora | [Link](https://huggingface.co/XLabs-AI/flux-RealismLora) |
-| 19  | flux-koda | [Link](https://huggingface.co/alvdansen/flux-koda) |
-| 20  | Cine-Aesthetic | [Link](https://huggingface.co/mgwr/Cine-Aesthetic) |
-| 21  | flux_cute3D | [Link](https://huggingface.co/SebastianBodza/flux_cute3D) |
-| 22  | flux_dreamscape | [Link](https://huggingface.co/bingbangboom/flux_dreamscape) |
-| 23  | Canopus-Cute-Kawaii-Flux-LoRA | [Link](https://huggingface.co/prithivMLmods/Canopus-Cute-Kawaii-Flux-LoRA) |
-| 24  | Flux-Pastel-Anime | [Link](https://huggingface.co/Raelina/Flux-Pastel-Anime) |
-| 25  | FLUX.1-dev-LoRA-Vector-Journey | [Link](https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-Vector-Journey) |
-| 26  | flux-miniature-worlds | [Link](https://huggingface.co/bingbangboom/flux-miniature-worlds) |
-| 27  | bingbangboom_flux_surf | [Link](https://huggingface.co/glif-loradex-trainer/bingbangboom_flux_surf) |
-| 28  | Canopus-Snoopy-Charlie-Brown-Flux-LoRA | [Link](https://huggingface.co/prithivMLmods/Canopus-Snoopy-Charlie-Brown-Flux-LoRA) |
-| 29  | sonny-anime-fixed | [Link](https://huggingface.co/alvdansen/sonny-anime-fixed) |
-| 30  | flux-multi-angle | [Link](https://huggingface.co/davisbro/flux-multi-angle) |
+### What Can You Do?
+- **Generate Hex Game Maker:** Create stunning hexagon grid overlays on any image with fully customizable parameters.
+- **AI-Powered Image Generation:** Use AI to generate images based on your prompts and apply hexagon grids to them.
+- **Color Exclusion:** Pick and exclude specific colors from your hexagon grid for a cleaner and more refined look.
+- **Interactive Customization:** Adjust hexagon size, border size, rotation, background color, and more in real-time.
+- **Depth and 3D Model Generation:** Generate depth maps and 3D models from your images for enhanced visualization.
+- **Image Filter [Look-Up Table (LUT)] Application:** Apply filters (LUTs) to your images for color grading and enhancement.
+- **Pre-rendered Maps:** Access a library of pre-rendered hexagon maps for quick and easy customization.
+- **Add Margins:** Add customizable margins around your images for a polished finish.
 
-& More ...
+### Why You'll Love It
+- **Fun and Easy to Use:** With an intuitive interface and real-time previews, creating hexagon grids has never been this fun!
+- **Endless Creativity:** Unleash your creativity with endless customization options and see your images transform in unique ways.
+- **Bee-Inspired Theme:** Enjoy a delightful yellow and purple theme inspired by bees and hexagons! 🐝
+- **Advanced AI Models:** Leverage advanced AI models and LoRA weights for high-quality image generation and customization.
 
-# Space Inspired From
+### Get Started
+1. **Upload or Generate an Image:** Start by uploading your own image or generate one using our AI-powered tool.
+2. **Customize Your Grid:** Play around with the settings to create the perfect hexagon grid overlay.
+3. **Download and Share:** Once you're happy with your creation, download it and share it with the world!
+
+### Advanced Features
+- **Generative AI Integration:** Utilize models like `black-forest-labs/FLUX.1-dev` and various LoRA weights for generating unique images.
+- **Pre-rendered Maps:** Access a library of pre-rendered hexagon maps for quick and easy customization.
+- **Image Filter [Look-Up Table (LUT)] Application:** Apply filters (LUTs) to your images for color grading and enhancement.
+- **Depth and 3D Model Generation:** Create depth maps and 3D models from your images for enhanced visualization.
+- **Add Margins:** Customize margins around your images for a polished finish.
+
+Join the hive and start creating with Hex Game Maker today!
+
+
+
+# AI Image Generation Space Inspired From
 
 | No. | Feature/Component | Description |
 | --- | ----------------- | ----------- |
@@ -67,4 +78,7 @@ thumbnail: >-
 | 11  | **Space URL**      | [flux-lora-the-explorer](https://huggingface.co/spaces/multimodalart/flux-lora-the-explorer) |
 
 
+## Contributions
+Thanks to [@Surn](https://huggingface.co/spaces/Surn/beeuty) for adding this gradio theme!
+Special Thanks to https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC as my endeavors to get the ZeroGPUs working had stopped me for 2 weeks with no help available. I was able to get the ZeroGPUs working with the help of this
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -4,13 +4,15 @@ import copy
 import time
 import random
 import logging
+from gradio.blocks import postprocess_update_dict
 import numpy as np
 from typing import Any, Dict, List, Optional, Union
+import logging
 
 import torch
 from PIL import Image
 import gradio as gr
-
+from tempfile import NamedTemporaryFile
 
 from diffusers import (
     DiffusionPipeline,
@@ -57,7 +59,11 @@ from modules.constants import (
     cards_alternating, 
     card_colors, 
     card_colors_alternating,
-    pre_rendered_maps_paths
+    pre_rendered_maps_paths,
+    PROMPTS,
+    NEGATIVE_PROMPTS,
+    TARGET_SIZE,
+    temp_files
 )
 from modules.excluded_colors import (
     add_color,
@@ -75,12 +81,14 @@ from modules.misc import (
 from modules.lora_details import (
     approximate_token_count,
     split_prompt_precisely,
+    upd_prompt_notes_by_index,
+    get_trigger_words_by_index
 )
 
 import spaces
 
 input_image_palette = []
-current_prerendered_image = gr.State("./images/images/Beeuty-1.png")
+current_prerendered_image = gr.State("./images/Beeuty-1.png")
 #---if workspace = local or colab---
 
 # Authenticate with Hugging Face
@@ -131,6 +139,7 @@ def flux_pipe_call_that_returns_an_iterable_of_images(
     self,
     prompt: Union[str, List[str]] = None,
     prompt_2: Optional[Union[str, List[str]]] = None,
+    negative_prompt: Optional[Union[str, List[str]]] = None,
     height: Optional[int] = None,
     width: Optional[int] = None,
     num_inference_steps: int = 28,
@@ -217,6 +226,7 @@ def flux_pipe_call_that_returns_an_iterable_of_images(
             continue
 
         timestep = t.expand(latents.shape[0]).to(latents.dtype)
+        print(f"Step {i + 1}/{num_inference_steps} - Timestep: {timestep.item()}\n")
 
         noise_pred = self.transformer(
             hidden_states=latents,
@@ -284,40 +294,52 @@ class calculateDuration:
         else:
             print(f"Elapsed time: {self.elapsed_time:.6f} seconds")
 
-def update_selection(evt: gr.SelectData, width, height):
+def update_selection(evt: gr.SelectData, width, height, aspect_ratio):
     selected_lora = loras[evt.index]
     new_placeholder = f"Type a prompt for {selected_lora['title']}"
+    new_aspect_ratio = aspect_ratio
     lora_repo = selected_lora["repo"]
     updated_text = f"### Selected: [{lora_repo}](https://huggingface.co/{lora_repo}) ✅"
+    # aspect will now use ratios if implemented, like 16:9, 4:3, 1:1, etc.
     if "aspect" in selected_lora:
-        if selected_lora["aspect"] == "portrait":
-            width = 768
-            height = 1024
-        elif selected_lora["aspect"] == "landscape":
-            width = 1024
-            height = 768
-        else:
-            width = 1024
-            height = 1024
+        try:
+            new_aspect_ratio = selected_lora["aspect"]
+            width, height = update_dimensions_on_ratio(new_aspect_ratio, height)
+        except Exception as e:
+            print(f"\nError in update selection aspect ratios:{e}\nSkipping")
+            new_aspect_ratio = aspect_ratio
+            width = width
+            height = height
     return (
         gr.update(placeholder=new_placeholder),
         updated_text,
         evt.index,
         width,
         height,
+        new_aspect_ratio,
+        upd_prompt_notes_by_index(evt.index)
     )
 
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=120,progress=gr.Progress(track_tqdm=True))
 def generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scale, progress):
     pipe.to("cuda")
     generator = torch.Generator(device="cuda").manual_seed(seed)
-    if approximate_token_count(prompt_mash) > 76:
+    flash_attention_enabled = torch.backends.cuda.flash_sdp_enabled()
+    if flash_attention_enabled:
+        pipe.attn_implementation="flash_attention_2"
+    print(f"\nGenerating image with prompt: {prompt_mash}\n")
+    approx_tokens= approximate_token_count(prompt_mash)
+    if approx_tokens > 76:
+        print(f"\nSplitting prompt due to length: {approx_tokens}\n")
         prompt, prompt2 = split_prompt_precisely(prompt_mash)
+    else:
+        prompt = prompt_mash
+        prompt2 = None
     with calculateDuration("Generating image"):
         # Generate image
         for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
             prompt=prompt,
-            prompt2=prompt2,
+            prompt_2=prompt2,
             num_inference_steps=steps,
             guidance_scale=cfg_scale,
             width=width,
@@ -329,15 +351,24 @@ def generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scal
         ):
             yield img
 
-def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps, cfg_scale, width, height, lora_scale, seed):
+def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps, cfg_scale, width, height, lora_scale, seed, progress):
     generator = torch.Generator(device="cuda").manual_seed(seed)
     pipe_i2i.to("cuda")
+    flash_attention_enabled = torch.backends.cuda.flash_sdp_enabled()
+    if flash_attention_enabled:
+        pipe_i2i.attn_implementation="flash_attention_2"
     image_input = load_image(image_input_path)
-    if approximate_token_count(prompt_mash) > 76:
+    print(f"\nGenerating image with prompt: {prompt_mash} and {image_input_path}\n")
+    approx_tokens= approximate_token_count(prompt_mash)
+    if approx_tokens > 76:
+        print(f"\nSplitting prompt due to length: {approx_tokens}\n")
         prompt, prompt2 = split_prompt_precisely(prompt_mash)
+    else:
+        prompt = prompt_mash
+        prompt2 = None
     final_image = pipe_i2i(
         prompt=prompt,
-        prompt2=prompt2,
+        prompt_2=prompt2,
         image=image_input,
         strength=image_strength,
         num_inference_steps=steps,
@@ -350,10 +381,21 @@ def generate_image_to_image(prompt_mash, image_input_path, image_strength, steps
     ).images[0]
     return final_image 
 
-@spaces.GPU(duration=120)
-def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, progress=gr.Progress(track_tqdm=True)):
+@spaces.GPU(duration=140)
+def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, enlarge, use_conditioned_image=False, progress=gr.Progress(track_tqdm=True)):
     if selected_index is None:
         raise gr.Error("You must select a LoRA before proceeding.🧨")
+    print(f"input Image: {image_input}\n")
+    # handle selecting a conditioned image from the gallery
+    global current_prerendered_image
+    conditioned_image=None
+    if use_conditioned_image:
+        print(f"Conditioned path: {current_prerendered_image.value}.. converting to RGB\n")
+        # ensure the conditioned image is an image and not a string, cannot use RGBA
+        if isinstance(current_prerendered_image.value, str):
+            conditioned_image = open_image(current_prerendered_image.value).convert("RGB")
+            image_input = crop_and_resize_image(conditioned_image, width, height)
+            print(f"Conditioned Image: {image_input.size}.. converted to RGB and resized\n")
     selected_lora = loras[selected_index]
     lora_path = selected_lora["repo"]
     trigger_word = selected_lora["trigger_word"]
@@ -389,7 +431,15 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
             
     if(image_input is not None):
         print(f"\nGenerating image to image with seed: {seed}\n")
-        final_image = generate_image_to_image(prompt_mash, image_input, image_strength, steps, cfg_scale, width, height, lora_scale, seed)
+        final_image = generate_image_to_image(prompt_mash, image_input, image_strength, steps, cfg_scale, width, height, lora_scale, seed, progress)
+        if enlarge:
+            upscaled_image = upscale_image(final_image, max(1.0,min((TARGET_SIZE[0]/width),(TARGET_SIZE[1]/height))))
+            # Save the upscaled image to a temporary file
+            with NamedTemporaryFile(delete=False, suffix=".png") as tmp_upscaled:
+                upscaled_image.save(tmp_upscaled.name, format="PNG")
+                temp_files.append(tmp_upscaled.name)
+                print(f"Upscaled image saved to {tmp_upscaled.name}")
+                final_image = tmp_upscaled.name
         yield final_image, seed, gr.update(visible=False)
     else:
         image_generator = generate_image(prompt_mash, steps, seed, cfg_scale, width, height, lora_scale, progress)
@@ -401,7 +451,15 @@ def run_lora(prompt, image_input, image_strength, cfg_scale, steps, selected_ind
             final_image = image
             progress_bar = f'<div class="progress-container"><div class="progress-bar" style="--current: {step_counter}; --total: {steps};"></div></div>'
             yield image, seed, gr.update(value=progress_bar, visible=True)
-            
+
+        if enlarge:
+            upscaled_image = upscale_image(final_image, max(1.0,min((TARGET_SIZE[0]/width),(TARGET_SIZE[1]/height))))
+            # Save the upscaled image to a temporary file
+            with NamedTemporaryFile(delete=False, suffix=".png") as tmp_upscaled:
+                upscaled_image.save(tmp_upscaled.name, format="PNG")
+                temp_files.append(tmp_upscaled.name)
+                print(f"Upscaled image saved to {tmp_upscaled.name}")
+                final_image = tmp_upscaled.name
         yield final_image, seed, gr.update(value=progress_bar, visible=False)
         
 def get_huggingface_safetensors(link):
@@ -486,6 +544,7 @@ def add_custom_lora(custom_lora):
 
 def remove_custom_lora():
     return gr.update(visible=False), gr.update(visible=False), gr.update(), "", None, ""
+
 def on_prerendered_gallery_selection(event_data: gr.SelectData):
     global current_prerendered_image
     selected_index = event_data.index
@@ -494,16 +553,27 @@ def on_prerendered_gallery_selection(event_data: gr.SelectData):
     current_prerendered_image.value = selected_image
     return current_prerendered_image
 
+def update_prompt_visibility(map_option):
+      is_visible = (map_option == "Prompt")
+      return (
+          gr.update(visible=is_visible),
+          gr.update(visible=is_visible),
+          gr.update(visible=is_visible)
+      )
+
+@spaces.GPU()
+def getVersions():
+    return versions_html()
 run_lora.zerogpu = True
-
+gr.set_static_paths(paths=["images/","images/images","images/prerendered","LUT/","fonts/", "assets/"])
 title = "Hex Game Maker"
-with gr.Blocks(css_paths="style_20250128.css", title=title, theme='Surn/beeuty', delete_cache=(7200, 7200)) as app:
+with gr.Blocks(css_paths="style_20250128.css", title=title, theme='Surn/beeuty', delete_cache=(43200, 43200), head_paths="head.htm") as app:
     with gr.Row():
         gr.Markdown("""
         # Hex Game Maker
         ## Transform Your Images into Mesmerizing Hexagon Grid Masterpieces! ⬢""", elem_classes="intro")
     with gr.Row():
-        with gr.Accordion("Welcome to Hex Game Maker, the ultimate tool for transforming your images into stunning hexagon grid artworks. Whether you're a tabletop game enthusiast, a digital artist, or someone who loves unique patterns, HexaGrid Creator has something for you.", open=False, elem_classes="intro"):
+        with gr.Accordion("Welcome to Hex Game Maker, the ultimate tool for transforming your images into stunning hexagon grid artworks. Whether you're a tabletop game enthusiast, a digital artist, or someone who loves unique patterns, Hex Game Maker has something for you.", open=False, elem_classes="intro"):
             gr.Markdown ("""
 
             ## Drop an image into the Input Image and get started!
@@ -541,7 +611,7 @@ with gr.Blocks(css_paths="style_20250128.css", title=title, theme='Surn/beeuty',
             - **Depth and 3D Model Generation:** Create depth maps and 3D models from your images for enhanced visualization.
             - **Add Margins:** Customize margins around your images for a polished finish.
 
-            Join the hive and start creating with HexaGrid Creator today!
+            Join the hive and start creating with Hex Game Maker today!
         
             """, elem_classes="intro")
     selected_index = gr.State(None)
@@ -635,58 +705,83 @@ with gr.Blocks(css_paths="style_20250128.css", title=title, theme='Surn/beeuty',
     with gr.Row():
         with gr.Accordion("Generative AI", open = False):
             with gr.Column(scale=3):
-                prompt = gr.Textbox(label="Prompt", lines=1, placeholder=":/ choose the LoRA and type the prompt ", value="top-down, (rectangular tabletop_map) alien planet map, Battletech_boardgame scifi world with forests, lakes, oceans, continents and snow at the top and bottom, (middle is dark, no_reflections, no_shadows), from directly above. From 100,000 feet looking straight down")
+                map_options = gr.Dropdown(
+                    label="Map Options",
+                    choices=list(PROMPTS.keys()),
+                    value="Alien Landscape",
+                    elem_classes="solid",
+                    scale=0
+                )
+                prompt = gr.Textbox(
+                    label="Prompt",
+                    visible=False,
+                    elem_classes="solid",
+                    value="top-down, (rectangular tabletop_map) alien planet map, Battletech_boardgame scifi world with forests, lakes, oceans, continents and snow at the top and bottom, (middle is dark, no_reflections, no_shadows), from directly above. From 100,000 feet looking straight down",
+                    lines=4
+                )
+                negative_prompt_textbox = gr.Textbox(
+                    label="Negative Prompt",
+                    visible=False,
+                    elem_classes="solid",
+                    value="Earth, low quality, bad anatomy, blurry, cropped, worst quality, shadows, people, humans, reflections, shadows, realistic map of the Earth, isometric, text"
+                )
+                prompt_notes_label = gr.Label(
+                    "Choose a LoRa style or add an image. YOU MUST CLEAR THE IMAGE TO START OVER ",
+                    elem_classes="solid centered small",
+                    show_label=False,
+                    visible=False
+                )
+                # Keep the change event to maintain functionality
+                map_options.change(
+                    fn=update_prompt_visibility,
+                    inputs=[map_options],
+                    outputs=[prompt, negative_prompt_textbox, prompt_notes_label]
+                )
+
             with gr.Column(scale=1, elem_id="gen_column"):
-                generate_button = gr.Button("Generate", variant="primary", elem_id="gen_btn")
+                generate_button = gr.Button("Generate From Promp and LoRa Style", variant="primary", elem_id="gen_btn")
             with gr.Row():
                 with gr.Column(scale=0):
                     selected_info = gr.Markdown("")
-                    gallery = gr.Gallery(
+                    lora_gallery = gr.Gallery(
                         [(item["image"], item["title"]) for item in loras],
                         label="LoRA Styles",
                         allow_preview=False,
                         columns=3,
-                        elem_id="gallery",
+                        elem_id="lora_gallery",
                         show_share_button=False
                     )
-                    with gr.Group():
-                        custom_lora = gr.Textbox(label="Enter Custom LoRA", placeholder="prithivMLmods/Canopus-LoRA-Flux-Anime")
-                        gr.Markdown("[Check the list of FLUX LoRA's](https://huggingface.co/models?other=base_model:adapter:black-forest-labs/FLUX.1-dev)", elem_id="lora_list")
-                    custom_lora_info = gr.HTML(visible=False)
-                    custom_lora_button = gr.Button("Remove custom LoRA", visible=False)
+                    with gr.Accordion("Custom LoRA", open=False):
+                        with gr.Group():
+                            custom_lora = gr.Textbox(label="Enter Custom LoRA", placeholder="prithivMLmods/Canopus-LoRA-Flux-Anime")
+                            gr.Markdown("[Check the list of FLUX LoRA's](https://huggingface.co/models?other=base_model:adapter:black-forest-labs/FLUX.1-dev)", elem_id="lora_list")
+                        custom_lora_info = gr.HTML(visible=False)
+                        custom_lora_button = gr.Button("Remove custom LoRA", visible=False)
                 with gr.Column(scale=2):
-                    # conditioning_image = gr.Image(label="Conditioning Image",
-                    #     type="filepath",
-                    #     interactive=True,
-                    #     elem_classes="centered solid imgcontainer",
-                    #     key="imgConditioning",
-                    #     image_mode=None,
-                    #     format="PNG", 
-                    #     show_download_button=True
-                    # )
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            # Gallery from PRE_RENDERED_IMAGES GOES HERE
-                            prerendered_image_gallery = gr.Gallery(label="Image Gallery", show_label=True, value=build_prerendered_images(pre_rendered_maps_paths), elem_id="gallery", elem_classes="solid", type="filepath", columns=[3], rows=[3], preview=False ,object_fit="contain", height="auto", format="png",allow_preview=False)                            
-                        with gr.Column(scale=1):
-                            #image_guidance_stength = gr.Slider(label="Image Guidance Strength", minimum=0, maximum=1.0, value=0.25, step=0.01, interactive=True)
-                            replace_input_image_button = gr.Button(
-                                "Replace Input Image",
-                                elem_id="prerendered_replace_input_image_button",
-                                elem_classes="solid"
-                            )                        
-                            generate_input_image_from_gallery = gr.Button(
-                                "Generate AI Image from Gallery",
-                                elem_id="generate_input_image_from_gallery",
-                                elem_classes="solid"
-                            )
+                    with gr.Accordion("Template Image Styles", open = False):
+                        with gr.Row():
+                            with gr.Column(scale=1):
+                                # Gallery from PRE_RENDERED_IMAGES GOES HERE
+                                prerendered_image_gallery = gr.Gallery(label="Image Gallery", show_label=True, value=build_prerendered_images(pre_rendered_maps_paths), elem_id="gallery", elem_classes="solid", type="filepath", columns=[3], rows=[3], preview=False ,object_fit="contain", height="auto", format="png",allow_preview=False)                            
+                            with gr.Column(scale=1):
+                                #image_guidance_stength = gr.Slider(label="Image Guidance Strength", minimum=0, maximum=1.0, value=0.25, step=0.01, interactive=True)
+                                replace_input_image_button = gr.Button(
+                                    "Replace Input Image",
+                                    elem_id="prerendered_replace_input_image_button",
+                                    elem_classes="solid"
+                                )                        
+                                generate_input_image_from_gallery = gr.Button(
+                                    "Generate AI Image from Gallery",
+                                    elem_id="generate_input_image_from_gallery",
+                                    elem_classes="solid"
+                                )
                     with gr.Accordion("Advanced Settings", open=False):
                         with gr.Row():
-                            image_strength = gr.Slider(label="Denoise Strength", info="Lower means more image influence", minimum=0.1, maximum=1.0, step=0.01, value=0.75)
+                            image_strength = gr.Slider(label="Image Guidance Strength (prompt percentage)", info="Lower means more image influence", minimum=0.1, maximum=1.0, step=0.01, value=0.8)
                         with gr.Column():
                             with gr.Row():
-                                cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, step=0.5, value=3.5)
-                                steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=28)
+                                cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, step=0.5, value=4.5)
+                                steps = gr.Slider(label="Steps", minimum=1, maximum=50, step=1, value=30)
                 
                             with gr.Row():
                                 negative_prompt_textbox = gr.Textbox(
@@ -698,59 +793,71 @@ with gr.Blocks(css_paths="style_20250128.css", title=title, theme='Surn/beeuty',
                                 # Add Dropdown for sizing of Images, height and width based on selection. Options are 16x9, 16x10, 4x5, 1x1
                                 # The values of height and width are based on common resolutions for each aspect ratio
                                 # Default to 16x9, 1024x576
-                                image_size_ratio = gr.Dropdown(label="Image Size", choices=["16:9", "16:10", "4:5", "4:3", "2:1","3:2","1:1", "9:16", "10:16", "5:4", "3:4","1:2", "2:3"], value="16:9", elem_classes="solid", type="value", scale=0, interactive=True)
-                                width = gr.Slider(label="Width", minimum=256, maximum=1536, step=64, value=576)
-                                height = gr.Slider(label="Height", minimum=256, maximum=2560, step=16, value=1024, interactive=False)
+                                image_size_ratio = gr.Dropdown(label="Image Aspect Ratio", choices=["16:9", "16:10", "4:5", "4:3", "2:1","3:2","1:1", "9:16", "10:16", "5:4", "3:4","1:2", "2:3"], value="16:9", elem_classes="solid", type="value", scale=0, interactive=True)
+                                width = gr.Slider(label="Width", minimum=256, maximum=2560, step=16, value=1024, interactive=False)
+                                height = gr.Slider(label="Height", minimum=256, maximum=1536, step=64, value=512)
+                                enlarge_to_default = gr.Checkbox(label="Auto Enlarge to Default Size", value=False)
                                 image_size_ratio.change(
                                     fn=update_dimensions_on_ratio,
-                                    inputs=[image_size_ratio, width],
+                                    inputs=[image_size_ratio, height],
                                     outputs=[width, height]
                                 )
-                                width.change(
-                                    fn=lambda *args: update_dimensions_on_ratio(*args)[1],
-                                    inputs=[image_size_ratio, width],
-                                    outputs=[height]
+                                height.change(
+                                    fn=lambda *args: update_dimensions_on_ratio(*args)[0],
+                                    inputs=[image_size_ratio, height],
+                                    outputs=[width]
                                 )
                             with gr.Row():
                                 randomize_seed = gr.Checkbox(True, label="Randomize seed")
                                 seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0, randomize=True)
-                                lora_scale = gr.Slider(label="LoRA Scale", minimum=0, maximum=3, step=0.01, value=0.95)
+                                lora_scale = gr.Slider(label="LoRA Scale", minimum=0, maximum=3, step=0.01, value=1.01)
     with gr.Row():
-        gr.HTML(value=versions_html(), visible=True, elem_id="versions")
+        gr.HTML(value=getVersions(), visible=True, elem_id="versions")
 
     # Event Handlers
+    #use conditioned_image as the input_image for generate_input_image_click
+    generate_input_image_from_gallery.click(
+        fn=run_lora,
+        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, enlarge_to_default, gr.State(True)],
+        outputs=[input_image, seed, progress_bar], scroll_to_output=True
+    )
     prerendered_image_gallery.select(
         fn=on_prerendered_gallery_selection, 
         inputs=None, 
-        outputs=[gr.State(current_prerendered_image)],  # Update the state with the selected image
-        show_api=False
+        outputs=gr.State(current_prerendered_image),  # Update the state with the selected image
+        show_api=False, scroll_to_output=True
     )
-    # replace input image with selected gallery image
+    # replace input image with selected prerendered image gallery selection
     replace_input_image_button.click(
         lambda: current_prerendered_image.value,
         inputs=None,
         outputs=[input_image], scroll_to_output=True
     )
-    gallery.select(
+    lora_gallery.select(
         update_selection,
-        inputs=[width, height],
-        outputs=[prompt, selected_info, selected_index, width, height]
+        inputs=[width, height, image_size_ratio],
+        outputs=[prompt, selected_info, selected_index, width, height, image_size_ratio, prompt_notes_label]
     )
     custom_lora.input(
         add_custom_lora,
         inputs=[custom_lora],
-        outputs=[custom_lora_info, custom_lora_button, gallery, selected_info, selected_index, prompt]
+        outputs=[custom_lora_info, custom_lora_button, lora_gallery, selected_info, selected_index, prompt]
     )
     custom_lora_button.click(
         remove_custom_lora,
-        outputs=[custom_lora_info, custom_lora_button, gallery, selected_info, selected_index, custom_lora]
+        outputs=[custom_lora_info, custom_lora_button, lora_gallery, selected_info, selected_index, custom_lora]
     )
     gr.on(
         triggers=[generate_button.click, prompt.submit],
         fn=run_lora,
-        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale],
+        inputs=[prompt, input_image, image_strength, cfg_scale, steps, selected_index, randomize_seed, seed, width, height, lora_scale, enlarge_to_default, gr.State(False)],
         outputs=[input_image, seed, progress_bar]
     )
 
+logging.basicConfig(
+    format="[%(levelname)s] %(asctime)s %(message)s", level=logging.INFO
+)
+logging.info("Environment Variables: %s" % os.environ)
+
 app.queue()
 app.launch(allowed_paths=["assets","/","./assets","images","./images", "./images/prerendered"], favicon_path="./assets/favicon.ico", max_file_size="10mb")

assets/site.webmanifest

@@ -0,0 +1,19 @@
+{
+  "name": "Hex Game Maker",
+  "short_name": "HexGameMaker",
+  "icons": [
+    {
+      "src": "gradio_api/file=./assets/android-chrome-192x192.png",
+      "sizes": "192x192",
+      "type": "image/png"
+    },
+    {
+      "src": "gradio_api/file=./assets/android-chrome-512x512.png",
+      "sizes": "512x512",
+      "type": "image/png"
+    }
+  ],
+  "theme_color": "#ff00ff",
+  "background_color": "#ffffff",
+  "display": "standalone"
+}

head.htm

@@ -0,0 +1,4 @@
+<link rel="apple-touch-icon" sizes="180x180" href="gradio_api/file=./assets/apple-touch-icon.png">
+<link rel="icon" type="image/png" sizes="32x32" href="gradio_api/file=./assets/favicon-32x32.png">
+<link rel="icon" type="image/png" sizes="16x16" href="gradio_api/file=./assets/favicon-16x16.png">
+<link rel="manifest" href="gradio_api/file=./assets/site.webmanifest">

modules/constants.py

@@ -40,6 +40,7 @@ if not HF_API_TOKEN:
 
 default_lut_example_img = "./LUT/daisy.jpg"
 MAX_SEED = np.iinfo(np.int32).max
+TARGET_SIZE = (2688,1536)
 
 PROMPTS = {
     "BorderBlack": "Top-down view of a hexagon-based alien map with black borders. Features rivers, mountains, volcanoes, and snow at top and bottom. Colors: light blue, green, tan, brown. No reflections or shadows. Partial hexes on edges are black.",
@@ -514,6 +515,18 @@ LORAS = [
         "trigger_word": "A TOK composite photo of a person posing at different angles"
     },
     #31
+    {
+        "image": "https://huggingface.co/Cossale/Frames2-Flex.1/resolve/main/samples/1737567472380__000005000_2.jpg",
+        "title": "Backdrops v2",
+        "weights": "backdrops_v2.safetensors",
+        "adapter_name": "backdrops_v2",
+        "repo": "Cossale/Frames2-Flex.1",
+        "trigger_word": "FRM$",
+        "notes": "You should use FRM$ as trigger words.",
+        "parameters" :{
+            "num_inference_steps": "50"
+        }
+    },
     {
         "image": "https://huggingface.co/Borcherding/FLUX.1-dev-LoRA-FractalLand-v0.1/resolve/main/images/example_e2zoqwftv.png",
         "title" : "Fractal Land",
@@ -535,7 +548,7 @@ LORAS = [
         "weights": "disney_lora.safetensors",
         "trigger_word": "disney style",
         "trigger_position" : "append",
-        "notes": "You should use ',disney style' as trigger words at the end.  ",
+        "notes": "Use ',disney style' as trigger words at the end of prompt.  ",
         "parameters" :{
             "num_inference_steps": "30",
         }
@@ -547,7 +560,7 @@ LORAS = [
         "weights": "anime_lora.safetensors",
         "trigger_word": "anime",
         "trigger_position" : "append",
-        "notes": "You should use ',anime' as trigger words at the end.  ",
+        "notes": "Use ',anime' as trigger words at the end.  ",
         "parameters" :{
             "num_inference_steps": "30",
         }
@@ -559,7 +572,7 @@ LORAS = [
         "weights": "scenery_lora.safetensors",
         "trigger_word": "scenery style",
         "trigger_position" : "append",
-        "notes": "You should use ',scenery style' as trigger words at the end.  ",
+        "notes": "Use ',scenery style' as trigger words at the end.  ",
         "parameters" :{
             "num_inference_steps": "30",
         }
@@ -627,7 +640,14 @@ LORAS = [
         "image": "https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design/resolve/main/images/73e7db6a33550d05836ce285549de60075d05373c7b0660d631dac33.jpg",
         "title": "Logo Design",
         "repo": "Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design",
-        "trigger_word": "wablogo, logo, Minimalist"
+        "trigger_word": "wablogo, logo, Minimalist",
+        "notes": "You should use wablogo, logo, Minimalist as trigger words..",
+        "pipe" :{
+                "fuse_lora": {"lora_scale":0.8}
+        },
+        "parameters" :{
+                "num_inference_steps": "38"
+        }
     }, 
     #41
     #43

modules/lora_details.py

@@ -1,7 +1,43 @@
 # modules/lora_details.py
 
 import gradio as gr
-from modules.constants import LORA_DETAILS
+from modules.constants import LORA_DETAILS, LORAS
+def upd_prompt_notes_by_index(lora_index):
+    """
+    Updates the prompt_notes_label with the notes from LORAS based on index.
+
+    Args:
+        lora_index (int): The index of the selected LoRA model.
+
+    Returns:
+        gr.update: Updated Gradio label component with the notes.
+    """
+    try:
+        if LORAS[lora_index]:
+            notes = LORAS[lora_index].get('notes', None)
+            if notes is None:
+                trigger_word = LORAS[lora_index].get('trigger_word', "")
+                trigger_position = LORAS[lora_index].get('trigger_position', "")
+                notes = f"{trigger_position} '{trigger_word}' in prompt"
+    except IndexError:
+        notes = "Enter Prompt description of your image, \nusing models without LoRa may take a 30 minutes."
+    return gr.update(value=notes)
+
+def get_trigger_words_by_index(lora_index):
+    """
+    Retrieves the trigger words from LORAS for the specified index.
+
+    Args:
+        lora_index (int): The index of the selected LoRA model.
+
+    Returns:
+        str: The trigger words associated with the model, or an empty string if not found.
+    """
+    try:
+        trigger_words = LORAS[lora_index].get('trigger_word', "")
+    except IndexError:
+        trigger_words = ""
+    return trigger_words
 
 def upd_prompt_notes(model_textbox_value):
     """

modules/misc.py

@@ -56,7 +56,7 @@ def convert_ratio_to_dimensions(ratio, height=512, rotate90=False):
     Returns:
         tuple: A tuple containing the calculated (width, height) in pixels, both divisible by 16.
     """
-    base_height = 512
+    base_height = 256
     # Scale the height based on the provided height parameter
     # Ensure the height is at least base_height
     scaled_height = max(height, base_height)
@@ -70,13 +70,13 @@ def convert_ratio_to_dimensions(ratio, height=512, rotate90=False):
         adjusted_width, adjusted_height = adjusted_height, adjusted_width
     return adjusted_width, adjusted_height
 
-def update_dimensions_on_ratio(image_format, width):
-    # Convert image_format from a string split by ":" into two numbers
-    width_ratio, height_ratio = map(int, image_format.split(":"))
+def update_dimensions_on_ratio(aspect_ratio_str, height):
+    # Convert aspect_ratio from a string split by ":" into two numbers
+    width_ratio, height_ratio = map(int, aspect_ratio_str.split(":"))
     aspect_ratio = width_ratio / height_ratio
 
-    # Compute new width and height based on the aspect ratio and base width
-    new_width, new_height = convert_ratio_to_dimensions(aspect_ratio, width)
+    # Compute new width and height based on the aspect ratio and base height
+    new_width, new_height = convert_ratio_to_dimensions(aspect_ratio, height)
     return new_width, new_height
 
 # def install_torch():    

web-ui.bat

@@ -0,0 +1,13 @@
+set NVIDIA_VISIBLE_DEVICES=0
+set CUDA_VISIBLE_DEVICES=0
+set CUDA_MODULE_LOADING=LAZY
+set PYTORCH_CUDA_ALLOC_CONF= max_split_size_mb:256
+set XFORMERS_FORCE_DISABLE_TRITON=1
+set TF_ENABLE_ONEDNN_OPTS=0
+set USE_FLASH_ATTENTION=1
+set GIT_LFS_ENABLED=true
+set TEMP = e:\\TMP
+set TMPDIR = e:\\TMP
+set XDG_CACHE_HOME = E:\\cache
+python -m app
+pause